diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/block_dev.c | 58 | ||||
-rw-r--r-- | fs/btrfs/Kconfig | 1 | ||||
-rw-r--r-- | fs/btrfs/disk-io.c | 1 | ||||
-rw-r--r-- | fs/btrfs/inode.c | 24 | ||||
-rw-r--r-- | fs/btrfs/locking.c | 9 | ||||
-rw-r--r-- | fs/btrfs/ordered-data.c | 11 | ||||
-rw-r--r-- | fs/btrfs/volumes.c | 10 | ||||
-rw-r--r-- | fs/ceph/dir.c | 2 | ||||
-rw-r--r-- | fs/cifs/cifsfs.c | 11 | ||||
-rw-r--r-- | fs/cifs/cifsfs.h | 2 | ||||
-rw-r--r-- | fs/cifs/inode.c | 16 | ||||
-rw-r--r-- | fs/cifs/smb2file.c | 18 | ||||
-rw-r--r-- | fs/cifs/smb2ops.c | 53 | ||||
-rw-r--r-- | fs/cifs/smb2pdu.c | 46 | ||||
-rw-r--r-- | fs/cifs/smb2pdu.h | 4 | ||||
-rw-r--r-- | fs/cifs/smb2proto.h | 7 | ||||
-rw-r--r-- | fs/dcache.c | 100 | ||||
-rw-r--r-- | fs/fs_pin.c | 10 | ||||
-rw-r--r-- | fs/internal.h | 2 | ||||
-rw-r--r-- | fs/io_uring.c | 81 | ||||
-rw-r--r-- | fs/mount.h | 8 | ||||
-rw-r--r-- | fs/namespace.c | 161 | ||||
-rw-r--r-- | fs/nfs/super.c | 6 | ||||
-rw-r--r-- | fs/open.c | 19 |
24 files changed, 476 insertions, 184 deletions
diff --git a/fs/block_dev.c b/fs/block_dev.c index 4707dfff991b..c2a85b587922 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -345,15 +345,24 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) struct bio *bio; bool is_poll = (iocb->ki_flags & IOCB_HIPRI) != 0; bool is_read = (iov_iter_rw(iter) == READ), is_sync; + bool nowait = (iocb->ki_flags & IOCB_NOWAIT) != 0; loff_t pos = iocb->ki_pos; blk_qc_t qc = BLK_QC_T_NONE; - int ret = 0; + gfp_t gfp; + ssize_t ret; if ((pos | iov_iter_alignment(iter)) & (bdev_logical_block_size(bdev) - 1)) return -EINVAL; - bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, &blkdev_dio_pool); + if (nowait) + gfp = GFP_NOWAIT; + else + gfp = GFP_KERNEL; + + bio = bio_alloc_bioset(gfp, nr_pages, &blkdev_dio_pool); + if (!bio) + return -EAGAIN; dio = container_of(bio, struct blkdev_dio, bio); dio->is_sync = is_sync = is_sync_kiocb(iocb); @@ -375,7 +384,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) if (!is_poll) blk_start_plug(&plug); + ret = 0; for (;;) { + int err; + bio_set_dev(bio, bdev); bio->bi_iter.bi_sector = pos >> 9; bio->bi_write_hint = iocb->ki_hint; @@ -383,8 +395,10 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) bio->bi_end_io = blkdev_bio_end_io; bio->bi_ioprio = iocb->ki_ioprio; - ret = bio_iov_iter_get_pages(bio, iter); - if (unlikely(ret)) { + err = bio_iov_iter_get_pages(bio, iter); + if (unlikely(err)) { + if (!ret) + ret = err; bio->bi_status = BLK_STS_IOERR; bio_endio(bio); break; @@ -399,6 +413,14 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) task_io_account_write(bio->bi_iter.bi_size); } + /* + * Tell underlying layer to not block for resource shortage. + * And if we would have blocked, return error inline instead + * of through the bio->bi_end_io() callback. + */ + if (nowait) + bio->bi_opf |= (REQ_NOWAIT | REQ_NOWAIT_INLINE); + dio->size += bio->bi_iter.bi_size; pos += bio->bi_iter.bi_size; @@ -412,6 +434,11 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } if (polled) WRITE_ONCE(iocb->ki_cookie, qc); @@ -432,8 +459,20 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) atomic_inc(&dio->ref); } - submit_bio(bio); - bio = bio_alloc(GFP_KERNEL, nr_pages); + qc = submit_bio(bio); + if (qc == BLK_QC_T_EAGAIN) { + if (!ret) + ret = -EAGAIN; + goto error; + } + ret += bio->bi_iter.bi_size; + + bio = bio_alloc(gfp, nr_pages); + if (!bio) { + if (!ret) + ret = -EAGAIN; + goto error; + } } if (!is_poll) @@ -453,13 +492,16 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) } __set_current_state(TASK_RUNNING); +out: if (!ret) ret = blk_status_to_errno(dio->bio.bi_status); - if (likely(!ret)) - ret = dio->size; bio_put(&dio->bio); return ret; +error: + if (!is_poll) + blk_finish_plug(&plug); + goto out; } static ssize_t diff --git a/fs/btrfs/Kconfig b/fs/btrfs/Kconfig index 212b4a854f2c..38651fae7f21 100644 --- a/fs/btrfs/Kconfig +++ b/fs/btrfs/Kconfig @@ -4,6 +4,7 @@ config BTRFS_FS tristate "Btrfs filesystem support" select CRYPTO select CRYPTO_CRC32C + select LIBCRC32C select ZLIB_INFLATE select ZLIB_DEFLATE select LZO_COMPRESS diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 41a2bd2e0c56..5f7ee70b3d1a 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -4106,6 +4106,7 @@ void close_ctree(struct btrfs_fs_info *fs_info) percpu_counter_destroy(&fs_info->dev_replace.bio_counter); cleanup_srcu_struct(&fs_info->subvol_srcu); + btrfs_free_csum_hash(fs_info); btrfs_free_stripe_hash_table(fs_info); btrfs_free_ref_cache(fs_info); } diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 1af069a9a0c7..ee582a36653d 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -395,10 +395,31 @@ static noinline int add_async_extent(struct async_chunk *cow, return 0; } +/* + * Check if the inode has flags compatible with compression + */ +static inline bool inode_can_compress(struct inode *inode) +{ + if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW || + BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM) + return false; + return true; +} + +/* + * Check if the inode needs to be submitted to compression, based on mount + * options, defragmentation, properties or heuristics. + */ static inline int inode_need_compress(struct inode *inode, u64 start, u64 end) { struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); + if (!inode_can_compress(inode)) { + WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG), + KERN_ERR "BTRFS: unexpected compression for ino %llu\n", + btrfs_ino(BTRFS_I(inode))); + return 0; + } /* force compress */ if (btrfs_test_opt(fs_info, FORCE_COMPRESS)) return 1; @@ -1631,7 +1652,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page, } else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) { ret = run_delalloc_nocow(inode, locked_page, start, end, page_started, 0, nr_written); - } else if (!inode_need_compress(inode, start, end)) { + } else if (!inode_can_compress(inode) || + !inode_need_compress(inode, start, end)) { ret = cow_file_range(inode, locked_page, start, end, end, page_started, nr_written, 1, NULL); } else { diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c index 98fccce4208c..393eceda57c8 100644 --- a/fs/btrfs/locking.c +++ b/fs/btrfs/locking.c @@ -346,9 +346,12 @@ void btrfs_tree_unlock(struct extent_buffer *eb) if (blockers) { btrfs_assert_no_spinning_writers(eb); eb->blocking_writers--; - /* Use the lighter barrier after atomic */ - smp_mb__after_atomic(); - cond_wake_up_nomb(&eb->write_lock_wq); + /* + * We need to order modifying blocking_writers above with + * actually waking up the sleepers to ensure they see the + * updated value of blocking_writers + */ + cond_wake_up(&eb->write_lock_wq); } else { btrfs_assert_spinning_writers_put(eb); write_unlock(&eb->lock); diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c index 1744ba8b2754..ae7f64a8facb 100644 --- a/fs/btrfs/ordered-data.c +++ b/fs/btrfs/ordered-data.c @@ -985,13 +985,14 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, struct extent_state **cached_state) { struct btrfs_ordered_extent *ordered; - struct extent_state *cachedp = NULL; + struct extent_state *cache = NULL; + struct extent_state **cachedp = &cache; if (cached_state) - cachedp = *cached_state; + cachedp = cached_state; while (1) { - lock_extent_bits(tree, start, end, &cachedp); + lock_extent_bits(tree, start, end, cachedp); ordered = btrfs_lookup_ordered_range(inode, start, end - start + 1); if (!ordered) { @@ -1001,10 +1002,10 @@ void btrfs_lock_and_flush_ordered_range(struct extent_io_tree *tree, * aren't exposing it outside of this function */ if (!cached_state) - refcount_dec(&cachedp->refs); + refcount_dec(&cache->refs); break; } - unlock_extent_cached(tree, start, end, &cachedp); + unlock_extent_cached(tree, start, end, cachedp); btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1); btrfs_put_ordered_extent(ordered); } diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a13ddba1ebc3..d74b74ca07af 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5941,6 +5941,7 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, u64 stripe_len; u64 raid56_full_stripe_start = (u64)-1; int data_stripes; + int ret = 0; ASSERT(op != BTRFS_MAP_DISCARD); @@ -5961,8 +5962,8 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, btrfs_crit(fs_info, "stripe math has gone wrong, stripe_offset=%llu offset=%llu start=%llu logical=%llu stripe_len=%llu", stripe_offset, offset, em->start, logical, stripe_len); - free_extent_map(em); - return -EINVAL; + ret = -EINVAL; + goto out; } /* stripe_offset is the offset of this block in its stripe */ @@ -6009,7 +6010,10 @@ int btrfs_get_io_geometry(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, io_geom->stripe_offset = stripe_offset; io_geom->raid56_stripe_offset = raid56_full_stripe_start; - return 0; +out: + /* once for us */ + free_extent_map(em); + return ret; } static int __btrfs_map_block(struct btrfs_fs_info *fs_info, diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index aab29f48c62d..4ca0b8ff9a72 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1267,7 +1267,7 @@ __dentry_leases_walk(struct ceph_mds_client *mdsc, if (!spin_trylock(&dentry->d_lock)) continue; - if (dentry->d_lockref.count < 0) { + if (__lockref_is_dead(&dentry->d_lockref)) { list_del_init(&di->lease_list); goto next; } diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 270d3c58fb3b..3289b566463f 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1104,6 +1104,10 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, goto out; } + rc = -EOPNOTSUPP; + if (!target_tcon->ses->server->ops->copychunk_range) + goto out; + /* * Note: cifs case is easier than btrfs since server responsible for * checks for proper open modes and file type and if it wants @@ -1115,11 +1119,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid, /* should we flush first and last page first */ truncate_inode_pages(&target_inode->i_data, 0); - if (target_tcon->ses->server->ops->copychunk_range) + rc = file_modified(dst_file); + if (!rc) rc = target_tcon->ses->server->ops->copychunk_range(xid, smb_file_src, smb_file_target, off, len, destoff); - else - rc = -EOPNOTSUPP; + + file_accessed(src_file); /* force revalidate of size and timestamps of target file now * that target is updated on the server diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index aea005703785..4b21a90015a9 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -152,5 +152,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CONFIG_CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "2.20" +#define CIFS_VERSION "2.21" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 1bffe029fb66..56ca4b8ccaba 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -2406,6 +2406,8 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) struct inode *inode = d_inode(direntry); struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb); struct cifsInodeInfo *cifsInode = CIFS_I(inode); + struct cifsFileInfo *wfile; + struct cifs_tcon *tcon; char *full_path = NULL; int rc = -EACCES; __u32 dosattr = 0; @@ -2452,6 +2454,20 @@ cifs_setattr_nounix(struct dentry *direntry, struct iattr *attrs) mapping_set_error(inode->i_mapping, rc); rc = 0; + if (attrs->ia_valid & ATTR_MTIME) { + rc = cifs_get_writable_file(cifsInode, false, &wfile); + if (!rc) { + tcon = tlink_tcon(wfile->tlink); + rc = tcon->ses->server->ops->flush(xid, tcon, &wfile->fid); + cifsFileInfo_put(wfile); + if (rc) + return rc; + } else if (rc != -EBADF) + return rc; + else + rc = 0; + } + if (attrs->ia_valid & ATTR_SIZE) { rc = cifs_set_file_size(inode, attrs, xid, full_path); if (rc != 0) diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index 54bffb2a1786..e6a1fc72018f 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -88,14 +88,20 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms, } if (buf) { - /* open response does not have IndexNumber field - get it */ - rc = SMB2_get_srv_num(xid, oparms->tcon, fid->persistent_fid, + /* if open response does not have IndexNumber field - get it */ + if (smb2_data->IndexNumber == 0) { + rc = SMB2_get_srv_num(xid, oparms->tcon, + fid->persistent_fid, fid->volatile_fid, &smb2_data->IndexNumber); - if (rc) { - /* let get_inode_info disable server inode numbers */ - smb2_data->IndexNumber = 0; - rc = 0; + if (rc) { + /* + * let get_inode_info disable server inode + * numbers + */ + smb2_data->IndexNumber = 0; + rc = 0; + } } move_smb2_info_to_cifs(buf, smb2_data); } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 0cdc4e47ca87..a5bc1b671c12 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -694,8 +694,51 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) smb2_set_related(&rqst[1]); + /* + * We do not hold the lock for the open because in case + * SMB2_open needs to reconnect, it will end up calling + * cifs_mark_open_files_invalid() which takes the lock again + * thus causing a deadlock + */ + + mutex_unlock(&tcon->crfid.fid_mutex); rc = compound_send_recv(xid, ses, flags, 2, rqst, resp_buftype, rsp_iov); + mutex_lock(&tcon->crfid.fid_mutex); + + /* + * Now we need to check again as the cached root might have + * been successfully re-opened from a concurrent process + */ + + if (tcon->crfid.is_valid) { + /* work was already done */ + + /* stash fids for close() later */ + struct cifs_fid fid = { + .persistent_fid = pfid->persistent_fid, + .volatile_fid = pfid->volatile_fid, + }; + + /* + * caller expects this func to set pfid to a valid + * cached root, so we copy the existing one and get a + * reference. + */ + memcpy(pfid, tcon->crfid.fid, sizeof(*pfid)); + kref_get(&tcon->crfid.refcount); + + mutex_unlock(&tcon->crfid.fid_mutex); + + if (rc == 0) { + /* close extra handle outside of crit sec */ + SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid); + } + goto oshr_free; + } + + /* Cached root is still invalid, continue normaly */ + if (rc) goto oshr_exit; @@ -711,11 +754,12 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) tcon->crfid.is_valid = true; kref_init(&tcon->crfid.refcount); + /* BB TBD check to see if oplock level check can be removed below */ if (o_rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) { kref_get(&tcon->crfid.refcount); - oplock = smb2_parse_lease_state(server, o_rsp, - &oparms.fid->epoch, - oparms.fid->lease_key); + smb2_parse_contexts(server, o_rsp, + &oparms.fid->epoch, + oparms.fid->lease_key, &oplock, NULL); } else goto oshr_exit; @@ -729,8 +773,9 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid) (char *)&tcon->crfid.file_all_info)) tcon->crfid.file_all_info_is_valid = 1; - oshr_exit: +oshr_exit: mutex_unlock(&tcon->crfid.fid_mutex); +oshr_free: SMB2_open_free(&rqst[0]); SMB2_query_info_free(&rqst[1]); free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index f58e4dc3987b..c8cd7b6cdda2 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1873,10 +1873,21 @@ create_reconnect_durable_buf(struct cifs_fid *fid) return buf; } -__u8 -smb2_parse_lease_state(struct TCP_Server_Info *server, +static void +parse_query_id_ctxt(struct create_context *cc, struct smb2_file_all_info *buf) +{ + struct create_on_disk_id *pdisk_id = (struct create_on_disk_id *)cc; + + cifs_dbg(FYI, "parse query id context 0x%llx 0x%llx\n", + pdisk_id->DiskFileId, pdisk_id->VolumeId); + buf->IndexNumber = pdisk_id->DiskFileId; +} + +void +smb2_parse_contexts(struct TCP_Server_Info *server, struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key) + unsigned int *epoch, char *lease_key, __u8 *oplock, + struct smb2_file_all_info *buf) { char *data_offset; struct create_context *cc; @@ -1884,15 +1895,24 @@ smb2_parse_lease_state(struct TCP_Server_Info *server, unsigned int remaining; char *name; + *oplock = 0; data_offset = (char *)rsp + le32_to_cpu(rsp->CreateContextsOffset); remaining = le32_to_cpu(rsp->CreateContextsLength); cc = (struct create_context *)data_offset; + + /* Initialize inode number to 0 in case no valid data in qfid context */ + if (buf) + buf->IndexNumber = 0; + while (remaining >= sizeof(struct create_context)) { name = le16_to_cpu(cc->NameOffset) + (char *)cc; if (le16_to_cpu(cc->NameLength) == 4 && - strncmp(name, "RqLs", 4) == 0) - return server->ops->parse_lease_buf(cc, epoch, - lease_key); + strncmp(name, SMB2_CREATE_REQUEST_LEASE, 4) == 0) + *oplock = server->ops->parse_lease_buf(cc, epoch, + lease_key); + else if (buf && (le16_to_cpu(cc->NameLength) == 4) && + strncmp(name, SMB2_CREATE_QUERY_ON_DISK_ID, 4) == 0) + parse_query_id_ctxt(cc, buf); next = le32_to_cpu(cc->Next); if (!next) @@ -1901,7 +1921,10 @@ smb2_parse_lease_state(struct TCP_Server_Info *server, cc = (struct create_context *)((char *)cc + next); } - return 0; + if (rsp->OplockLevel != SMB2_OPLOCK_LEVEL_LEASE) + *oplock = rsp->OplockLevel; + + return; } static int @@ -2588,12 +2611,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path, buf->DeletePending = 0; } - if (rsp->OplockLevel == SMB2_OPLOCK_LEVEL_LEASE) - *oplock = smb2_parse_lease_state(server, rsp, - &oparms->fid->epoch, - oparms->fid->lease_key); - else - *oplock = rsp->OplockLevel; + + smb2_parse_contexts(server, rsp, &oparms->fid->epoch, + oparms->fid->lease_key, oplock, buf); creat_exit: SMB2_open_free(&rqst); free_rsp_buf(resp_buftype, rsp); diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 7e2e782f8edd..747de9317659 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -818,7 +818,9 @@ struct durable_reconnect_context_v2 { } __packed; /* See MS-SMB2 2.2.14.2.9 */ -struct on_disk_id { +struct create_on_disk_id { + struct create_context ccontext; + __u8 Name[8]; __le64 DiskFileId; __le64 VolumeId; __u32 Reserved[4]; diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 52df125e9189..07ca72486cfa 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -228,9 +228,10 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *); extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *, enum securityEnum); -extern __u8 smb2_parse_lease_state(struct TCP_Server_Info *server, - struct smb2_create_rsp *rsp, - unsigned int *epoch, char *lease_key); +extern void smb2_parse_contexts(struct TCP_Server_Info *server, + struct smb2_create_rsp *rsp, + unsigned int *epoch, char *lease_key, + __u8 *oplock, struct smb2_file_all_info *buf); extern int smb3_encryption_required(const struct cifs_tcon *tcon); extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length, struct kvec *iov, unsigned int min_buf_size); diff --git a/fs/dcache.c b/fs/dcache.c index f41121e5d1ec..e88cf0554e65 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -861,6 +861,32 @@ void dput(struct dentry *dentry) } EXPORT_SYMBOL(dput); +static void __dput_to_list(struct dentry *dentry, struct list_head *list) +__must_hold(&dentry->d_lock) +{ + if (dentry->d_flags & DCACHE_SHRINK_LIST) { + /* let the owner of the list it's on deal with it */ + --dentry->d_lockref.count; + } else { + if (dentry->d_flags & DCACHE_LRU_LIST) + d_lru_del(dentry); + if (!--dentry->d_lockref.count) + d_shrink_add(dentry, list); + } +} + +void dput_to_list(struct dentry *dentry, struct list_head *list) +{ + rcu_read_lock(); + if (likely(fast_dput(dentry))) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + if (!retain_dentry(dentry)) + __dput_to_list(dentry, list); + spin_unlock(&dentry->d_lock); +} /* This must be called with d_lock held */ static inline void __dget_dlock(struct dentry *dentry) @@ -1067,7 +1093,7 @@ out: return false; } -static void shrink_dentry_list(struct list_head *list) +void shrink_dentry_list(struct list_head *list) { while (!list_empty(list)) { struct dentry *dentry, *parent; @@ -1089,18 +1115,9 @@ static void shrink_dentry_list(struct list_head *list) rcu_read_unlock(); d_shrink_del(dentry); parent = dentry->d_parent; + if (parent != dentry) + __dput_to_list(parent, list); __dentry_kill(dentry); - if (parent == dentry) - continue; - /* - * We need to prune ancestors too. This is necessary to prevent - * quadratic behavior of shrink_dcache_parent(), but is also - * expected to be beneficial in reducing dentry cache - * fragmentation. - */ - dentry = parent; - while (dentry && !lockref_put_or_lock(&dentry->d_lockref)) - dentry = dentry_kill(dentry); } } @@ -1445,8 +1462,11 @@ out: struct select_data { struct dentry *start; + union { + long found; + struct dentry *victim; + }; struct list_head dispose; - int found; }; static enum d_walk_ret select_collect(void *_data, struct dentry *dentry) @@ -1478,6 +1498,37 @@ out: return ret; } +static enum d_walk_ret select_collect2(void *_data, struct dentry *dentry) +{ + struct select_data *data = _data; + enum d_walk_ret ret = D_WALK_CONTINUE; + + if (data->start == dentry) + goto out; + + if (dentry->d_flags & DCACHE_SHRINK_LIST) { + if (!dentry->d_lockref.count) { + rcu_read_lock(); + data->victim = dentry; + return D_WALK_QUIT; + } + } else { + if (dentry->d_flags & DCACHE_LRU_LIST) + d_lru_del(dentry); + if (!dentry->d_lockref.count) + d_shrink_add(dentry, &data->dispose); + } + /* + * We can return to the caller if we have found some (this + * ensures forward progress). We'll be coming back to find + * the rest. + */ + if (!list_empty(&data->dispose)) + ret = need_resched() ? D_WALK_QUIT : D_WALK_NORETRY; +out: + return ret; +} + /** * shrink_dcache_parent - prune dcache * @parent: parent of entries to prune @@ -1487,12 +1538,9 @@ out: void shrink_dcache_parent(struct dentry *parent) { for (;;) { - struct select_data data; + struct select_data data = {.start = parent}; INIT_LIST_HEAD(&data.dispose); - data.start = parent; - data.found = 0; - d_walk(parent, &data, select_collect); if (!list_empty(&data.dispose)) { @@ -1503,6 +1551,24 @@ void shrink_dcache_parent(struct dentry *parent) cond_resched(); if (!data.found) break; + data.victim = NULL; + d_walk(parent, &data, select_collect2); + if (data.victim) { + struct dentry *parent; + spin_lock(&data.victim->d_lock); + if (!shrink_lock_dentry(data.victim)) { + spin_unlock(&data.victim->d_lock); + rcu_read_unlock(); + } else { + rcu_read_unlock(); + parent = data.victim->d_parent; + if (parent != data.victim) + __dput_to_list(parent, &data.dispose); + __dentry_kill(data.victim); + } + } + if (!list_empty(&data.dispose)) + shrink_dentry_list(&data.dispose); } } EXPORT_SYMBOL(shrink_dcache_parent); diff --git a/fs/fs_pin.c b/fs/fs_pin.c index a6497cf8ae53..47ef3c71ce90 100644 --- a/fs/fs_pin.c +++ b/fs/fs_pin.c @@ -19,20 +19,14 @@ void pin_remove(struct fs_pin *pin) spin_unlock_irq(&pin->wait.lock); } -void pin_insert_group(struct fs_pin *pin, struct vfsmount *m, struct hlist_head *p) +void pin_insert(struct fs_pin *pin, struct vfsmount *m) { spin_lock(&pin_lock); - if (p) - hlist_add_head(&pin->s_list, p); + hlist_add_head(&pin->s_list, &m->mnt_sb->s_pins); hlist_add_head(&pin->m_list, &real_mount(m)->mnt_pins); spin_unlock(&pin_lock); } -void pin_insert(struct fs_pin *pin, struct vfsmount *m) -{ - pin_insert_group(pin, m, &m->mnt_sb->s_pins); -} - void pin_kill(struct fs_pin *p) { wait_queue_entry_t wait; diff --git a/fs/internal.h b/fs/internal.h index ff5173212803..315fcd8d237c 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -157,6 +157,8 @@ extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern char *simple_dname(struct dentry *, char *, int); +extern void dput_to_list(struct dentry *, struct list_head *); +extern void shrink_dentry_list(struct list_head *); /* * read_write.c diff --git a/fs/io_uring.c b/fs/io_uring.c index e2a66e12fbc6..012bc0efb9d3 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -202,7 +202,7 @@ struct async_list { struct file *file; off_t io_end; - size_t io_pages; + size_t io_len; }; struct io_ring_ctx { @@ -333,7 +333,8 @@ struct io_kiocb { #define REQ_F_IO_DRAIN 16 /* drain existing IO first */ #define REQ_F_IO_DRAINED 32 /* drain done */ #define REQ_F_LINK 64 /* linked sqes */ -#define REQ_F_FAIL_LINK 128 /* fail rest of links */ +#define REQ_F_LINK_DONE 128 /* linked sqes done */ +#define REQ_F_FAIL_LINK 256 /* fail rest of links */ u64 user_data; u32 result; u32 sequence; @@ -429,7 +430,7 @@ static inline bool io_sequence_defer(struct io_ring_ctx *ctx, if ((req->flags & (REQ_F_IO_DRAIN|REQ_F_IO_DRAINED)) != REQ_F_IO_DRAIN) return false; - return req->sequence > ctx->cached_cq_tail + ctx->sq_ring->dropped; + return req->sequence != ctx->cached_cq_tail + ctx->sq_ring->dropped; } static struct io_kiocb *io_get_deferred_req(struct io_ring_ctx *ctx) @@ -632,6 +633,7 @@ static void io_req_link_next(struct io_kiocb *req) nxt->flags |= REQ_F_LINK; } + nxt->flags |= REQ_F_LINK_DONE; INIT_WORK(&nxt->work, io_sq_wq_submit_work); queue_work(req->ctx->sqo_wq, &nxt->work); } @@ -1064,8 +1066,44 @@ static int io_import_fixed(struct io_ring_ctx *ctx, int rw, */ offset = buf_addr - imu->ubuf; iov_iter_bvec(iter, rw, imu->bvec, imu->nr_bvecs, offset + len); - if (offset) - iov_iter_advance(iter, offset); + + if (offset) { + /* + * Don't use iov_iter_advance() here, as it's really slow for + * using the latter parts of a big fixed buffer - it iterates + * over each segment manually. We can cheat a bit here, because + * we know that: + * + * 1) it's a BVEC iter, we set it up + * 2) all bvecs are PAGE_SIZE in size, except potentially the + * first and last bvec + * + * So just find our index, and adjust the iterator afterwards. + * If the offset is within the first bvec (or the whole first + * bvec, just use iov_iter_advance(). This makes it easier + * since we can just skip the first segment, which may not + * be PAGE_SIZE aligned. + */ + const struct bio_vec *bvec = imu->bvec; + + if (offset <= bvec->bv_len) { + iov_iter_advance(iter, offset); + } else { + unsigned long seg_skip; + + /* skip first vec */ + offset -= bvec->bv_len; + seg_skip = 1 + (offset >> PAGE_SHIFT); + + iter->bvec = bvec + seg_skip; + iter->nr_segs -= seg_skip; + iter->count -= (seg_skip << PAGE_SHIFT); + iter->iov_offset = offset & ~PAGE_MASK; + if (iter->iov_offset) + iter->count -= iter->iov_offset; + } + } + return 0; } @@ -1120,28 +1158,26 @@ static void io_async_list_note(int rw, struct io_kiocb *req, size_t len) off_t io_end = kiocb->ki_pos + len; if (filp == async_list->file && kiocb->ki_pos == async_list->io_end) { - unsigned long max_pages; + unsigned long max_bytes; /* Use 8x RA size as a decent limiter for both reads/writes */ - max_pages = filp->f_ra.ra_pages; - if (!max_pages) - max_pages = VM_READAHEAD_PAGES; - max_pages *= 8; - - /* If max pages are exceeded, reset the state */ - len >>= PAGE_SHIFT; - if (async_list->io_pages + len <= max_pages) { + max_bytes = filp->f_ra.ra_pages << (PAGE_SHIFT + 3); + if (!max_bytes) + max_bytes = VM_READAHEAD_PAGES << (PAGE_SHIFT + 3); + + /* If max len are exceeded, reset the state */ + if (async_list->io_len + len <= max_bytes) { req->flags |= REQ_F_SEQ_PREV; - async_list->io_pages += len; + async_list->io_len += len; } else { io_end = 0; - async_list->io_pages = 0; + async_list->io_len = 0; } } /* New file? Reset state. */ if (async_list->file != filp) { - async_list->io_pages = 0; + async_list->io_len = 0; async_list->file = filp; } async_list->io_end = io_end; @@ -1630,6 +1666,8 @@ static int io_poll_add(struct io_kiocb *req, const struct io_uring_sqe *sqe) INIT_LIST_HEAD(&poll->wait.entry); init_waitqueue_func_entry(&poll->wait, io_poll_wake); + INIT_LIST_HEAD(&req->list); + mask = vfs_poll(poll->file, &ipt.pt) & poll->events; spin_lock_irq(&ctx->completion_lock); @@ -1844,6 +1882,10 @@ restart: /* async context always use a copy of the sqe */ kfree(sqe); + /* req from defer and link list needn't decrease async cnt */ + if (req->flags & (REQ_F_IO_DRAINED | REQ_F_LINK_DONE)) + goto out; + if (!async_list) break; if (!list_empty(&req_list)) { @@ -1891,6 +1933,7 @@ restart: } } +out: if (cur_mm) { set_fs(old_fs); unuse_mm(cur_mm); @@ -1917,6 +1960,10 @@ static bool io_add_to_prev_work(struct async_list *list, struct io_kiocb *req) ret = true; spin_lock(&list->lock); list_add_tail(&req->list, &list->list); + /* + * Ensure we see a simultaneous modification from io_sq_wq_submit_work() + */ + smp_mb(); if (!atomic_read(&list->cnt)) { list_del_init(&req->list); ret = false; diff --git a/fs/mount.h b/fs/mount.h index 6250de544760..711a4093e475 100644 --- a/fs/mount.h +++ b/fs/mount.h @@ -58,7 +58,10 @@ struct mount { struct mount *mnt_master; /* slave is on master->mnt_slave_list */ struct mnt_namespace *mnt_ns; /* containing namespace */ struct mountpoint *mnt_mp; /* where is it mounted */ - struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ + union { + struct hlist_node mnt_mp_list; /* list mounts with the same mountpoint */ + struct hlist_node mnt_umount; + }; struct list_head mnt_umounting; /* list entry for umount propagation */ #ifdef CONFIG_FSNOTIFY struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks; @@ -68,8 +71,7 @@ struct mount { int mnt_group_id; /* peer group identifier */ int mnt_expiry_mark; /* true if marked for expiry */ struct hlist_head mnt_pins; - struct fs_pin mnt_umount; - struct dentry *mnt_ex_mountpoint; + struct hlist_head mnt_stuck_children; } __randomize_layout; #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */ diff --git a/fs/namespace.c b/fs/namespace.c index f0d664adb9ba..d28d30b13043 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -70,6 +70,8 @@ static struct hlist_head *mount_hashtable __read_mostly; static struct hlist_head *mountpoint_hashtable __read_mostly; static struct kmem_cache *mnt_cache __read_mostly; static DECLARE_RWSEM(namespace_sem); +static HLIST_HEAD(unmounted); /* protected by namespace_sem */ +static LIST_HEAD(ex_mountpoints); /* protected by namespace_sem */ /* /sys/fs */ struct kobject *fs_kobj; @@ -170,14 +172,6 @@ unsigned int mnt_get_count(struct mount *mnt) #endif } -static void drop_mountpoint(struct fs_pin *p) -{ - struct mount *m = container_of(p, struct mount, mnt_umount); - dput(m->mnt_ex_mountpoint); - pin_remove(p); - mntput(&m->mnt); -} - static struct mount *alloc_vfsmnt(const char *name) { struct mount *mnt = kmem_cache_zalloc(mnt_cache, GFP_KERNEL); @@ -215,7 +209,7 @@ static struct mount *alloc_vfsmnt(const char *name) INIT_LIST_HEAD(&mnt->mnt_slave); INIT_HLIST_NODE(&mnt->mnt_mp_list); INIT_LIST_HEAD(&mnt->mnt_umounting); - init_fs_pin(&mnt->mnt_umount, drop_mountpoint); + INIT_HLIST_HEAD(&mnt->mnt_stuck_children); } return mnt; @@ -740,7 +734,7 @@ mountpoint: /* Add the new mountpoint to the hash table */ read_seqlock_excl(&mount_lock); - new->m_dentry = dentry; + new->m_dentry = dget(dentry); new->m_count = 1; hlist_add_head(&new->m_hash, mp_hash(dentry)); INIT_HLIST_HEAD(&new->m_list); @@ -753,7 +747,11 @@ done: return mp; } -static void put_mountpoint(struct mountpoint *mp) +/* + * vfsmount lock must be held. Additionally, the caller is responsible + * for serializing calls for given disposal list. + */ +static void __put_mountpoint(struct mountpoint *mp, struct list_head *list) { if (!--mp->m_count) { struct dentry *dentry = mp->m_dentry; @@ -761,11 +759,18 @@ static void put_mountpoint(struct mountpoint *mp) spin_lock(&dentry->d_lock); dentry->d_flags &= ~DCACHE_MOUNTED; spin_unlock(&dentry->d_lock); + dput_to_list(dentry, list); hlist_del(&mp->m_hash); kfree(mp); } } +/* called with namespace_lock and vfsmount lock */ +static void put_mountpoint(struct mountpoint *mp) +{ + __put_mountpoint(mp, &ex_mountpoints); +} + static inline int check_mnt(struct mount *mnt) { return mnt->mnt_ns == current->nsproxy->mnt_ns; @@ -796,25 +801,17 @@ static void __touch_mnt_namespace(struct mnt_namespace *ns) /* * vfsmount lock must be held for write */ -static void unhash_mnt(struct mount *mnt) +static struct mountpoint *unhash_mnt(struct mount *mnt) { + struct mountpoint *mp; mnt->mnt_parent = mnt; mnt->mnt_mountpoint = mnt->mnt.mnt_root; list_del_init(&mnt->mnt_child); hlist_del_init_rcu(&mnt->mnt_hash); hlist_del_init(&mnt->mnt_mp_list); - put_mountpoint(mnt->mnt_mp); + mp = mnt->mnt_mp; mnt->mnt_mp = NULL; -} - -/* - * vfsmount lock must be held for write - */ -static void detach_mnt(struct mount *mnt, struct path *old_path) -{ - old_path->dentry = mnt->mnt_mountpoint; - old_path->mnt = &mnt->mnt_parent->mnt; - unhash_mnt(mnt); + return mp; } /* @@ -822,9 +819,7 @@ static void detach_mnt(struct mount *mnt, struct path *old_path) */ static void umount_mnt(struct mount *mnt) { - /* old mountpoint will be dropped when we can do that */ - mnt->mnt_ex_mountpoint = mnt->mnt_mountpoint; - unhash_mnt(mnt); + put_mountpoint(unhash_mnt(mnt)); } /* @@ -836,7 +831,7 @@ void mnt_set_mountpoint(struct mount *mnt, { mp->m_count++; mnt_add_count(mnt, 1); /* essentially, that's mntget */ - child_mnt->mnt_mountpoint = dget(mp->m_dentry); + child_mnt->mnt_mountpoint = mp->m_dentry; child_mnt->mnt_parent = mnt; child_mnt->mnt_mp = mp; hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list); @@ -863,7 +858,6 @@ static void attach_mnt(struct mount *mnt, void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt) { struct mountpoint *old_mp = mnt->mnt_mp; - struct dentry *old_mountpoint = mnt->mnt_mountpoint; struct mount *old_parent = mnt->mnt_parent; list_del_init(&mnt->mnt_child); @@ -873,22 +867,6 @@ void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct m attach_mnt(mnt, parent, mp); put_mountpoint(old_mp); - - /* - * Safely avoid even the suggestion this code might sleep or - * lock the mount hash by taking advantage of the knowledge that - * mnt_change_mountpoint will not release the final reference - * to a mountpoint. - * - * During mounting, the mount passed in as the parent mount will - * continue to use the old mountpoint and during unmounting, the - * old mountpoint will continue to exist until namespace_unlock, - * which happens well after mnt_change_mountpoint. - */ - spin_lock(&old_mountpoint->d_lock); - old_mountpoint->d_lockref.count--; - spin_unlock(&old_mountpoint->d_lock); - mnt_add_count(old_parent, -1); } @@ -1103,19 +1081,22 @@ static struct mount *clone_mnt(struct mount *old, struct dentry *root, static void cleanup_mnt(struct mount *mnt) { + struct hlist_node *p; + struct mount *m; /* - * This probably indicates that somebody messed - * up a mnt_want/drop_write() pair. If this - * happens, the filesystem was probably unable - * to make r/w->r/o transitions. - */ - /* + * The warning here probably indicates that somebody messed + * up a mnt_want/drop_write() pair. If this happens, the + * filesystem was probably unable to make r/w->r/o transitions. * The locking used to deal with mnt_count decrement provides barriers, * so mnt_get_writers() below is safe. */ WARN_ON(mnt_get_writers(mnt)); if (unlikely(mnt->mnt_pins.first)) mnt_pin_kill(mnt); + hlist_for_each_entry_safe(m, p, &mnt->mnt_stuck_children, mnt_umount) { + hlist_del(&m->mnt_umount); + mntput(&m->mnt); + } fsnotify_vfsmount_delete(&mnt->mnt); dput(mnt->mnt.mnt_root); deactivate_super(mnt->mnt.mnt_sb); @@ -1141,6 +1122,8 @@ static DECLARE_DELAYED_WORK(delayed_mntput_work, delayed_mntput); static void mntput_no_expire(struct mount *mnt) { + LIST_HEAD(list); + rcu_read_lock(); if (likely(READ_ONCE(mnt->mnt_ns))) { /* @@ -1181,10 +1164,12 @@ static void mntput_no_expire(struct mount *mnt) if (unlikely(!list_empty(&mnt->mnt_mounts))) { struct mount *p, *tmp; list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts, mnt_child) { - umount_mnt(p); + __put_mountpoint(unhash_mnt(p), &list); + hlist_add_head(&p->mnt_umount, &mnt->mnt_stuck_children); } } unlock_mount_hash(); + shrink_dentry_list(&list); if (likely(!(mnt->mnt.mnt_flags & MNT_INTERNAL))) { struct task_struct *task = current; @@ -1370,22 +1355,29 @@ int may_umount(struct vfsmount *mnt) EXPORT_SYMBOL(may_umount); -static HLIST_HEAD(unmounted); /* protected by namespace_sem */ - static void namespace_unlock(void) { struct hlist_head head; + struct hlist_node *p; + struct mount *m; + LIST_HEAD(list); hlist_move_list(&unmounted, &head); + list_splice_init(&ex_mountpoints, &list); up_write(&namespace_sem); + shrink_dentry_list(&list); + if (likely(hlist_empty(&head))) return; synchronize_rcu_expedited(); - group_pin_kill(&head); + hlist_for_each_entry_safe(m, p, &head, mnt_umount) { + hlist_del(&m->mnt_umount); + mntput(&m->mnt); + } } static inline void namespace_lock(void) @@ -1471,9 +1463,6 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) p->mnt.mnt_flags |= MNT_SYNC_UMOUNT; disconnect = disconnect_mount(p, how); - - pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt, - disconnect ? &unmounted : NULL); if (mnt_has_parent(p)) { mnt_add_count(p->mnt_parent, -1); if (!disconnect) { @@ -1484,6 +1473,8 @@ static void umount_tree(struct mount *mnt, enum umount_tree_flags how) } } change_mnt_propagation(p, MS_PRIVATE); + if (disconnect) + hlist_add_head(&p->mnt_umount, &unmounted); } } @@ -1626,15 +1617,15 @@ void __detach_mounts(struct dentry *dentry) namespace_lock(); lock_mount_hash(); mp = lookup_mountpoint(dentry); - if (IS_ERR_OR_NULL(mp)) + if (!mp) goto out_unlock; event++; while (!hlist_empty(&mp->m_list)) { mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list); if (mnt->mnt.mnt_flags & MNT_UMOUNT) { - hlist_add_head(&mnt->mnt_umount.s_list, &unmounted); umount_mnt(mnt); + hlist_add_head(&mnt->mnt_umount, &unmounted); } else umount_tree(mnt, UMOUNT_CONNECTED); } @@ -2046,7 +2037,7 @@ int count_mounts(struct mnt_namespace *ns, struct mount *mnt) static int attach_recursive_mnt(struct mount *source_mnt, struct mount *dest_mnt, struct mountpoint *dest_mp, - struct path *parent_path) + bool moving) { struct user_namespace *user_ns = current->nsproxy->mnt_ns->user_ns; HLIST_HEAD(tree_list); @@ -2064,7 +2055,7 @@ static int attach_recursive_mnt(struct mount *source_mnt, return PTR_ERR(smp); /* Is there space to add these mounts to the mount namespace? */ - if (!parent_path) { + if (!moving) { err = count_mounts(ns, source_mnt); if (err) goto out; @@ -2083,8 +2074,8 @@ static int attach_recursive_mnt(struct mount *source_mnt, } else { lock_mount_hash(); } - if (parent_path) { - detach_mnt(source_mnt, parent_path); + if (moving) { + unhash_mnt(source_mnt); attach_mnt(source_mnt, dest_mnt, dest_mp); touch_mnt_namespace(source_mnt->mnt_ns); } else { @@ -2182,7 +2173,7 @@ static int graft_tree(struct mount *mnt, struct mount *p, struct mountpoint *mp) d_is_dir(mnt->mnt.mnt_root)) return -ENOTDIR; - return attach_recursive_mnt(mnt, p, mp, NULL); + return attach_recursive_mnt(mnt, p, mp, false); } /* @@ -2575,11 +2566,11 @@ out: static int do_move_mount(struct path *old_path, struct path *new_path) { - struct path parent_path = {.mnt = NULL, .dentry = NULL}; struct mnt_namespace *ns; struct mount *p; struct mount *old; - struct mountpoint *mp; + struct mount *parent; + struct mountpoint *mp, *old_mp; int err; bool attached; @@ -2589,7 +2580,9 @@ static int do_move_mount(struct path *old_path, struct path *new_path) old = real_mount(old_path->mnt); p = real_mount(new_path->mnt); + parent = old->mnt_parent; attached = mnt_has_parent(old); + old_mp = old->mnt_mp; ns = old->mnt_ns; err = -EINVAL; @@ -2617,7 +2610,7 @@ static int do_move_mount(struct path *old_path, struct path *new_path) /* * Don't move a mount residing in a shared parent. */ - if (attached && IS_MNT_SHARED(old->mnt_parent)) + if (attached && IS_MNT_SHARED(parent)) goto out; /* * Don't move a mount tree containing unbindable mounts to a destination @@ -2633,18 +2626,21 @@ static int do_move_mount(struct path *old_path, struct path *new_path) goto out; err = attach_recursive_mnt(old, real_mount(new_path->mnt), mp, - attached ? &parent_path : NULL); + attached); if (err) goto out; /* if the mount is moved, it should no longer be expire * automatically */ list_del_init(&old->mnt_expire); + if (attached) + put_mountpoint(old_mp); out: unlock_mount(mp); if (!err) { - path_put(&parent_path); - if (!attached) + if (attached) + mntput_no_expire(parent); + else free_mnt_ns(ns); } return err; @@ -3589,8 +3585,8 @@ EXPORT_SYMBOL(path_is_under); SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, const char __user *, put_old) { - struct path new, old, parent_path, root_parent, root; - struct mount *new_mnt, *root_mnt, *old_mnt; + struct path new, old, root; + struct mount *new_mnt, *root_mnt, *old_mnt, *root_parent, *ex_parent; struct mountpoint *old_mp, *root_mp; int error; @@ -3619,9 +3615,11 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, new_mnt = real_mount(new.mnt); root_mnt = real_mount(root.mnt); old_mnt = real_mount(old.mnt); + ex_parent = new_mnt->mnt_parent; + root_parent = root_mnt->mnt_parent; if (IS_MNT_SHARED(old_mnt) || - IS_MNT_SHARED(new_mnt->mnt_parent) || - IS_MNT_SHARED(root_mnt->mnt_parent)) + IS_MNT_SHARED(ex_parent) || + IS_MNT_SHARED(root_parent)) goto out4; if (!check_mnt(root_mnt) || !check_mnt(new_mnt)) goto out4; @@ -3638,7 +3636,6 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, goto out4; /* not a mountpoint */ if (!mnt_has_parent(root_mnt)) goto out4; /* not attached */ - root_mp = root_mnt->mnt_mp; if (new.mnt->mnt_root != new.dentry) goto out4; /* not a mountpoint */ if (!mnt_has_parent(new_mnt)) @@ -3649,10 +3646,9 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* make certain new is below the root */ if (!is_path_reachable(new_mnt, new.dentry, &root)) goto out4; - root_mp->m_count++; /* pin it so it won't go away */ lock_mount_hash(); - detach_mnt(new_mnt, &parent_path); - detach_mnt(root_mnt, &root_parent); + umount_mnt(new_mnt); + root_mp = unhash_mnt(root_mnt); /* we'll need its mountpoint */ if (root_mnt->mnt.mnt_flags & MNT_LOCKED) { new_mnt->mnt.mnt_flags |= MNT_LOCKED; root_mnt->mnt.mnt_flags &= ~MNT_LOCKED; @@ -3660,7 +3656,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, /* mount old root on put_old */ attach_mnt(root_mnt, old_mnt, old_mp); /* mount new_root on / */ - attach_mnt(new_mnt, real_mount(root_parent.mnt), root_mp); + attach_mnt(new_mnt, root_parent, root_mp); + mnt_add_count(root_parent, -1); touch_mnt_namespace(current->nsproxy->mnt_ns); /* A moved mount should not expire automatically */ list_del_init(&new_mnt->mnt_expire); @@ -3670,10 +3667,8 @@ SYSCALL_DEFINE2(pivot_root, const char __user *, new_root, error = 0; out4: unlock_mount(old_mp); - if (!error) { - path_put(&root_parent); - path_put(&parent_path); - } + if (!error) + mntput_no_expire(ex_parent); out3: path_put(&root); out2: diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 3683d2b1cc8e..628631e2e34f 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -457,10 +457,8 @@ int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) struct dentry *pd_dentry; pd_dentry = dget_parent(dentry); - if (pd_dentry != NULL) { - nfs_zap_caches(d_inode(pd_dentry)); - dput(pd_dentry); - } + nfs_zap_caches(d_inode(pd_dentry)); + dput(pd_dentry); } nfs_free_fattr(res.fattr); if (error < 0) diff --git a/fs/open.c b/fs/open.c index b5b80469b93d..a59abe3c669a 100644 --- a/fs/open.c +++ b/fs/open.c @@ -374,6 +374,25 @@ long do_faccessat(int dfd, const char __user *filename, int mode) override_cred->cap_permitted; } + /* + * The new set of credentials can *only* be used in + * task-synchronous circumstances, and does not need + * RCU freeing, unless somebody then takes a separate + * reference to it. + * + * NOTE! This is _only_ true because this credential + * is used purely for override_creds() that installs + * it as the subjective cred. Other threads will be + * accessing ->real_cred, not the subjective cred. + * + * If somebody _does_ make a copy of this (using the + * 'get_current_cred()' function), that will clear the + * non_rcu field, because now that other user may be + * expecting RCU freeing. But normal thread-synchronous + * cred accesses will keep things non-RCY. + */ + override_cred->non_rcu = 1; + old_cred = override_creds(override_cred); retry: res = user_path_at(dfd, filename, lookup_flags, &path); |